From 5a4dfb8a76f6b99a929df10c90865146c59717f8 Mon Sep 17 00:00:00 2001
From: krrr <guogaishiwo@gmail.com>
Date: Sat, 30 Apr 2022 11:20:04 +0800
Subject: [PATCH] Add new option to avoid cloudflare captcha
---
README.rst | 2 +-
nhentai/cmdline.py | 20 +++++++++++++-------
nhentai/command.py | 3 ---
nhentai/constant.py | 1 +
nhentai/utils.py | 12 ++++++++----
5 files changed, 23 insertions(+), 15 deletions(-)
diff --git a/README.rst b/README.rst
index 49e729d..86bb769 100644
--- a/README.rst
+++ b/README.rst
@@ -72,7 +72,7 @@ Set your nhentai cookie against captcha:
nhentai --cookie "YOUR COOKIE FROM nhentai.net"
-**NOTE**: The format of the cookie is `"csrftoken=TOKEN; sessionid=ID"`
+**NOTE**: The format of the cookie is `"csrftoken=TOKEN; sessionid=ID; cf_chl_2=CLOUDFLARE; cf_chl_prog=CLOUDFLARE; cf_clearance=CLOUDFLARE"`
| To get csrftoken and sessionid, first login to your nhentai account in web browser, then:
| (Chrome) |ve| |ld| More tools |ld| Developer tools |ld| Application |ld| Storage |ld| Cookies |ld| https://nhentai.net
diff --git a/nhentai/cmdline.py b/nhentai/cmdline.py
index 6c39ceb..8cca43d 100644
--- a/nhentai/cmdline.py
+++ b/nhentai/cmdline.py
@@ -109,7 +109,9 @@ def cmd_parser():
# nhentai options
parser.add_option('--cookie', type='str', dest='cookie', action='store',
- help='set cookie of nhentai to bypass Google recaptcha')
+ help='set cookie of nhentai to bypass Cloudflare captcha')
+ parser.add_option('--useragent', type='str', dest='useragent', action='store',
+ help='set useragent to bypass Cloudflare captcha')
parser.add_option('--language', type='str', dest='language', action='store',
help='set default language to parse doujinshis')
parser.add_option('--clean-language', dest='clean_language', action='store_true', default=False,
@@ -148,20 +150,24 @@ def cmd_parser():
# --- set config ---
if args.cookie is not None:
constant.CONFIG['cookie'] = args.cookie
+ write_config()
logger.info('Cookie saved.')
- write_config()
exit(0)
-
- if args.language is not None:
- constant.CONFIG['language'] = args.language
- logger.info('Default language now set to \'{0}\''.format(args.language))
+ elif args.useragent is not None:
+ constant.CONFIG['useragent'] = args.useragent
write_config()
+ logger.info('Useragent saved.')
+ exit(0)
+ elif args.language is not None:
+ constant.CONFIG['language'] = args.language
+ write_config()
+ logger.info('Default language now set to \'{0}\''.format(args.language))
exit(0)
# TODO: search without language
if args.proxy is not None:
proxy_url = urlparse(args.proxy)
- if not args.proxy == '' and proxy_url.scheme not in ('http', 'https'):
+ if not args.proxy == '' and proxy_url.scheme not in ('http', 'https', 'socks5', 'socks5h', 'socks4', 'socks4a'):
logger.error('Invalid protocol \'{0}\' of proxy, ignored'.format(proxy_url.scheme))
exit(0)
else:
diff --git a/nhentai/command.py b/nhentai/command.py
index a6c91d0..e514144 100644
--- a/nhentai/command.py
+++ b/nhentai/command.py
@@ -93,9 +93,6 @@ def main():
doujinshi.downloader = downloader
doujinshi.download()
- doujinshi.downloader = downloader
- doujinshi.download()
-
if options.generate_metadata:
table = doujinshi.table
generate_metadata_file(options.output_dir, table, doujinshi)
diff --git a/nhentai/constant.py b/nhentai/constant.py
index 10feab8..e100898 100644
--- a/nhentai/constant.py
+++ b/nhentai/constant.py
@@ -34,6 +34,7 @@ CONFIG = {
'cookie': '',
'language': '',
'template': '',
+ 'useragent': 'nhentai command line client (https://github.com/RicterZ/nhentai)'
}
LANGUAGEISO ={
diff --git a/nhentai/utils.py b/nhentai/utils.py
index e0a5b4d..8354637 100644
--- a/nhentai/utils.py
+++ b/nhentai/utils.py
@@ -17,7 +17,7 @@ def request(method, url, **kwargs):
session = requests.Session()
session.headers.update({
'Referer': constant.LOGIN_URL,
- 'User-Agent': 'nhentai command line client (https://github.com/RicterZ/nhentai)',
+ 'User-Agent': constant.CONFIG['useragent'],
'Cookie': constant.CONFIG['cookie']
})
@@ -28,10 +28,14 @@ def request(method, url, **kwargs):
def check_cookie():
- response = request('get', constant.BASE_URL).text
- username = re.findall('"/users/\d+/(.*?)"', response)
+ response = request('get', constant.BASE_URL)
+ if response.status_code == 503 and 'cf-browser-verification' in response.text:
+ logger.error('Blocked by Cloudflare captcha, please set your cookie and useragent')
+ exit(-1)
+
+ username = re.findall('"/users/\d+/(.*?)"', response.text)
if not username:
- logger.error('Cannot get your username, please check your cookie or use `nhentai --cookie` to set your cookie')
+ logger.warning('Cannot get your username, please check your cookie or use `nhentai --cookie` to set your cookie')
else:
logger.info('Login successfully! Your username: {}'.format(username[0]))